phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
11363 commits 1603 branches 645 tags 320 MiB
Commit graph

1344 commits

Author SHA1 Message Date
Krrish Dholakia
bc66ef9d5c fix(utils.py): fix aws secret manager + support key_management_settings 
fixes the aws secret manager implementation and allows the user to set which keys they want to check thr
ough it
 2024-03-16 16:47:50 -07:00
Krrish Dholakia
d8956e9255 fix(utils.py): initial commit for aws secret manager support 2024-03-16 14:37:46 -07:00
Krrish Dholakia
909341c4f2 fix(utils.py): async add to cache - for streaming 2024-03-15 18:25:40 -07:00
Krrish Dholakia
226953e1d8 feat(batch_redis_get.py): batch redis GET requests for a given key + call type 
reduces the number of GET requests we're making in high-throughput scenarios
 2024-03-15 14:40:11 -07:00
Krrish Dholakia
9909f44015 feat(utils.py): add native fireworks ai support 
addresses - https://github.com/BerriAI/litellm/issues/777, https://github.com/BerriAI/litellm/issues/2486
 2024-03-15 09:09:59 -07:00
Krrish Dholakia
a634424fb2 fix(utils.py): move to using litellm.modify_params to enable max output token trimming fix 2024-03-14 12:17:56 -07:00
Krrish Dholakia
234cdbbfef feat(prompt_injection_detection.py): support simple heuristic similarity check for prompt injection attacks 2024-03-13 10:32:21 -07:00
Krish Dholakia
9f2d540ebf
Merge pull request #2472 from BerriAI/litellm_anthropic_streaming_tool_calling 
fix(anthropic.py): support claude-3 streaming with function calling
 2024-03-12 21:36:01 -07:00
Ishaan Jaff
7b4f9691c7
Merge pull request #2479 from BerriAI/litellm_cohere_tool_call 
[FEAT Cohere/command-r tool calling
 2024-03-12 21:20:59 -07:00
Krrish Dholakia
d620b4dc5d fix(anthropic.py): bug fix 2024-03-12 19:32:42 -07:00
ishaan-jaff
b9bfc7c36c (fix) use cohere_chat optional params 2024-03-12 14:31:43 -07:00
Krish Dholakia
0d18f3c0ca
Merge pull request #2473 from BerriAI/litellm_fix_compatible_provider_model_name 
fix(openai.py): return model name with custom llm provider for openai-compatible endpoints (e.g. mistral, together ai, etc.)
 2024-03-12 12:58:29 -07:00
Krish Dholakia
1ba102c618
Merge pull request #2475 from BerriAI/litellm_azure_dall_e_3_cost_tracking 
fix(azure.py): support cost tracking for azure/dall-e-3
 2024-03-12 12:57:31 -07:00
ishaan-jaff
a18c941621 (fix) failing cohere test 2024-03-12 12:44:19 -07:00
ishaan-jaff
d136238f6f (v0) tool calling 2024-03-12 12:35:52 -07:00
Krrish Dholakia
d07c813ef9 test: add more logging for failing test 2024-03-12 11:15:14 -07:00
Ishaan Jaff
5172fb1de9
Merge pull request #2474 from BerriAI/litellm_support_command_r 
[New-Model] Cohere/command-r
 2024-03-12 11:11:56 -07:00
Krrish Dholakia
7dd94c802e fix(azure.py): support cost tracking for azure/dall-e-3 2024-03-12 10:55:54 -07:00
ishaan-jaff
e5bb65669d (feat) exception mapping for cohere_chat 2024-03-12 10:45:42 -07:00
Krrish Dholakia
0033613b9e fix(openai.py): return model name with custom llm provider for openai compatible endpoints 2024-03-12 10:30:10 -07:00
Krrish Dholakia
86ed0aaba8 fix(anthropic.py): support streaming with function calling 2024-03-12 09:52:11 -07:00
ishaan-jaff
223ac464d7 (fix) support streaming for azure/instruct models 2024-03-12 09:50:43 -07:00
Krrish Dholakia
312a9d8c26 fix(utils.py): support response_format for mistral ai api 2024-03-11 10:23:41 -07:00
Vince Loewe
7c38f992dc
Merge branch 'main' into main 2024-03-11 12:36:41 +09:00
Krish Dholakia
c7d0af0a2e
Merge pull request #2426 from BerriAI/litellm_whisper_cost_tracking 
feat: add cost tracking + caching for `/audio/transcription` calls
 2024-03-09 19:12:06 -08:00
Krrish Dholakia
1d15dde6de fix(utils.py): fix model setting in completion cost 2024-03-09 19:11:37 -08:00
Krrish Dholakia
8d2d51b625 fix(utils.py): fix model name checking 2024-03-09 18:22:26 -08:00
Krrish Dholakia
fa45c569fd feat: add cost tracking + caching for transcription calls 2024-03-09 15:43:38 -08:00
Krrish Dholakia
8b24ddcbbd fix(bedrock.py): enable claude-3 streaming 2024-03-09 14:02:27 -08:00
Krish Dholakia
caa99f43bf
Merge branch 'main' into litellm_load_balancing_transcription_endpoints 2024-03-08 23:08:47 -08:00
Krish Dholakia
e245b1c98a
Merge pull request #2401 from BerriAI/litellm_transcription_endpoints 
feat(main.py): support openai transcription endpoints
 2024-03-08 23:07:48 -08:00
Krrish Dholakia
fd52b502a6 fix(utils.py): *new* get_supported_openai_params() function 
Returns the supported openai params for a given model + provider
 2024-03-08 23:06:40 -08:00
Krrish Dholakia
aeb3cbc9b6 fix(utils.py): add additional providers to get_supported_openai_params 2024-03-08 23:06:40 -08:00
Krrish Dholakia
daa371ade9 fix(utils.py): add support for anthropic params in get_supported_openai_params 2024-03-08 23:06:40 -08:00
Krrish Dholakia
fac01f8481 fix(azure.py): add pre call logging for transcription calls 2024-03-08 22:23:21 -08:00
Krrish Dholakia
0fb7afe820 feat(proxy_server.py): working /audio/transcription endpoint 2024-03-08 18:20:27 -08:00
ishaan-jaff
0a538fe679 (feat) use no-log to disable per request logging 2024-03-08 16:56:20 -08:00
ishaan-jaff
ddd231a8c2 (feat) use no-log as a litellm param 2024-03-08 16:46:38 -08:00
ishaan-jaff
986a526790 (feat) disable logging per request 2024-03-08 16:25:54 -08:00
Krrish Dholakia
696eb54455 feat(main.py): support openai transcription endpoints 
enable user to load balance between openai + azure transcription endpoints
 2024-03-08 10:25:19 -08:00
Krrish Dholakia
0e7b30bec9 fix(utils.py): return function name for ollama_chat function calls 2024-03-08 08:01:10 -08:00
Krrish Dholakia
ec79482612 fix(utils.py): fix google ai studio timeout error raising 2024-03-06 21:12:04 -08:00
Krish Dholakia
38612ddd34
Merge pull request #2377 from BerriAI/litellm_team_level_model_groups 
feat(proxy_server.py): team based model aliases
 2024-03-06 21:03:53 -08:00
Krrish Dholakia
c0c3117dec fix(utils.py): fix get optional param embeddings 2024-03-06 20:47:05 -08:00
ishaan-jaff
0ee02e1ab9 (fix) vertex_ai test_vertex_projects optional params embedding 2024-03-06 20:33:25 -08:00
Krish Dholakia
cb8b30970b
Merge pull request #2347 from BerriAI/litellm_retry_rate_limited_requests 
feat(proxy_server.py): retry if virtual key is rate limited
 2024-03-06 19:23:11 -08:00
Krrish Dholakia
7e3734d037 test(test_completion.py): handle gemini timeout error 2024-03-06 19:05:39 -08:00
ishaan-jaff
d3818713ad (fix) dict changed size during iteration 2024-03-06 17:53:01 -08:00
Krrish Dholakia
7d824225a5 fix(utils.py): set status code for api error 2024-03-05 21:37:59 -08:00
Krrish Dholakia
a3a751ce62 fix(utils.py): fix mistral api exception mapping 2024-03-05 20:45:16 -08:00